Fast-Training Algorithm for Hidden-Layer Forward-Feed Neural Networks.

Abstract

A new training algorithm, based on the matrix pseudoinverse method, is shown to train hidden-layer, forward-feed neural networks with high accuracy in a short time for nonlinear time series prediction. The algorithm is applied to chaotic time series generated from the logistics map and the Mackey-Glass delay differential equation and compared to corresponding results generated using a backpropagation training algorithm. We demonstrate orders of magnitude shorter training time and comparable accuracy with the new algorithm and show forecasting and self-generation for these systems.

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1993
Accession Number
ADA269253

Entities

People

  • Charles M. Bowden
  • Chi C. Sung
  • Shawn D. Pethel

Organizations

  • United States Army Aviation and Missile Command

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Delphi Method
  • Demographic Cohorts
  • Differential Equations
  • Equations
  • Logistics
  • Mathematics
  • Neural Networks
  • Training

Fields of Study

  • Computer science

Readers

  • Linear Algebra
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks